© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8245
    Prev
    Next
    INDEX
    Explanations

    data acquisition and processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    禹
    -0.06
     Boul
    -0.06
    poi
    -0.06
    æ¦ľ
    -0.06
     Pag
    -0.06
    бÑĢ
    -0.06
    oplast
    -0.06
    ole
    -0.06
    å¡ijéĢł
    -0.06
    åIJĮä¸Ģ个
    -0.06
    POSITIVE LOGITS
     online
    0.10
    ÑĤÑĥÑģ
    0.08
    线ä¸Ĭ线
    0.08
    _online
    0.08
    online
    0.08
     offline
    0.08
     онлайн
    0.08
    åľ¨çº¿
    0.08
     Online
    0.08
    åľ¨ç·ļ
    0.08
    Activations Density 0.006%

    No Known Activations